Detection of Hemodynamic Characteristics Before Growth in Growing Cerebral Aneurysms by Analyzing Time-of-Flight Magnetic Resonance Angiography Images Alone: Preliminary Results

Evaluation of predictive models of aneurysm focal growth and bleb development using machine learning techniques

BACKGROUND

The presence of blebs increases the rupture risk of intracranial aneurysms (IAs).

OBJECTIVE

To evaluate whether cross-sectional bleb formation models can identify aneurysms with focalized enlargement in longitudinal series.

METHODS

Hemodynamic, geometric, and anatomical variables derived from computational fluid dynamics models of 2265 IAs from a cross-sectional dataset were used to train machine learning (ML) models for bleb development. ML algorithms, including logistic regression, random forest, bagging method, support vector machine, and K-nearest neighbors, were validated using an independent cross-sectional dataset of 266 IAs. The models' ability to identify aneurysms with focalized enlargement was evaluated using a separate longitudinal dataset of 174 IAs. Model performance was quantified by the area under the receiving operating characteristic curve (AUC), the sensitivity and specificity, positive predictive value, negative predictive value, F1 score, balanced accuracy, and misclassification error.

RESULTS

The final model, with three hemodynamic and four geometrical variables, along with aneurysm location and morphology, identified strong inflow jets, non-uniform wall shear stress with high peaks, larger sizes, and elongated shapes as indicators of a higher risk of focal growth over time. The logistic regression model demonstrated the best performance on the longitudinal series, achieving an AUC of 0.9, sensitivity of 85%, specificity of 75%, balanced accuracy of 80%, and a misclassification error of 21%.

CONCLUSIONS

Models trained with cross-sectional data can identify aneurysms prone to future focalized growth with good accuracy. These models could potentially be used as early indicators of future risk in clinical practice.

A preliminary study of relationship among the degree of internal carotid artery stenosis, wall shear stress on MR angiography and 18F-FDG uptake on PET/CT

BACKGROUND

This preliminary study was undertaken to evaluate relationship among the degree of internal carotid artery (ICA) stenosis, wall shear stress (WSS) by computational fluid dynamics (CFD) on magnetic resonance angiography (MRA) and 18F-FDG uptake of ICA on PET/CT.

METHODS

A total of 40 carotid arteries in 20 patients with carotid atherosclerotic disease were examined with MRA and 18F-FDG PET/CT. Atherosclerotic risk factors were assessed in all patients. Degree of ICA stenosis was calculated according to NASCET method. CFD analysis was performed and maximum WSS (WSSmax) was measured. 18F-FDG uptake in ICA was quantified using maximum target-to-blood pool ratio (TBRmax).

RESULTS

Atherosclerotic risk factors did not affect imaging findings. There were significant correlations between WSSmax and degree of ICA stenosis (ρ = .81, P < .001), WSSmax and TBRmax (ρ = .64, P < .001), and TBRmax and degree of ICA stenosis (ρ = .50, P = .001).

CONCLUSIONS

These preliminary results indicate that there may be significant correlations among the degree of ICA stenosis, WSSmax and TBRmax in patients with carotid artery stenosis.

Newly Identified Hemodynamic Parameter to Predict Thin-Walled Regions of Unruptured Cerebral Aneurysms Using Computational Fluid Dynamics Analysis

BACKGROUND

The thin-walled regions (TIWRs) of intracranial aneurysms have a high risk of rupture during surgical manipulation. They have been reported to be predicted by wall shear stress and pressure (PS) based on computational fluid dynamics analysis, although this remains controversial. In this study, we investigated whether the oscillatory shear index (OSI) can predict TIWRs.

METHODS

Twenty-five unruptured aneurysms were retrospectively analyzed; the position and orientation of the computational fluid dynamics color maps were adjusted to match the intraoperative micrographs. The red area on the aneurysm wall was defined as TIWR, and if most of the regions on the color map corresponding to TIWR were OSI low (lower quartile range), time-averaged wall shear stress (TAWSS) high, or PS high (upper quartile range), each region was defined as a matched region and divided by the total number of TIWRs to calculate the match rate. In addition, the mean values of OSI, TAWSS, and PS corresponding to TIWRs were quantitatively compared with those in adjacent thick-walled regions.

RESULTS

Among 27 TIWRs of 25 aneurysms, 23, 10, and 14 regions had low OSI, high TAWSS, and high PS regions (match rate: 85.2%, 37.0%, and 51.9%), respectively. Receiver operating characteristic curve analysis demonstrated that OSI was the most effective hemodynamic parameter (area under the curve, 0.881), followed by TAWSS (0.798). Multivariate analysis showed that OSI was a significant independent predictor of TIWRs (odds ratio, 18.30 [95% CI, 3.2800-102.00], P < 0.001).

CONCLUSIONS

OSI may be a unique predictor for TIWRs. Low OSI strongly corresponds with TIWRs of intracranial aneurysms.

Pointwise encoding time reduction with radial acquisition in subtraction-based magnetic resonance angiography to assess saccular unruptured intracranial aneurysms at 3 Tesla

PURPOSE

To investigate the clinical utility of pointwise encoding time reduction with radial acquisition in subtraction-based magnetic resonance angiography (PETRA-MRA) and time-of-flight magnetic resonance angiography (TOF-MRA) to evaluate saccular unruptured intracranial aneurysms (UIAs).

METHODS

A total of 49 patients with 54 TOF-MRA-identified saccular UIAs were enrolled. The morphologic parameters, contrast-to-noise-ratios (CNRs), and sharpness of aneurysms were measured using PETRA-MRA and TOF-MRA. Two radiologists independently evaluated subjective image scores, focusing on aneurysm signal homogeneities and sharpness depictions using a 4-point scale: 4, excellent; 3, good; 2, poor; 1, not assessable. PETRA-MRA and TOF-MRA acoustic noises were measured.

RESULTS

All aneurysms were detected with PETRA-MRA. The morphologic parameters of 15 patients evaluated with PETRA-MRA were more closely correlated with those receiving computed tomography angiography over those receiving TOF-MRA. No significant differences between PETRA-MRA and TOF-MRA parameters were seen in the 54 UIAs (p > 0.10), excluding those with inflow angles (p < 0.05). In four patients with inflow angles on PETRA-MRA, the angles were more closely related to those of digital subtraction angiography than those of TOF-MRA. CNRs between TOF-MRA and PETRA-MRA were comparable (p = 0.068), and PETRA-MRA sharpness values and subjective image scores were significantly higher than those of TOF-MRA (p < 0.001). Inter-observer agreements were excellent for both PETRA-MRA and TOF-MRA (intraclass correlation coefficients were 0.90 and 0.97, respectively). The acoustic noise levels of PETRA-MRA were much lower than those of TOF-MRA (59 vs.73 dB, p < 0.01).

CONCLUSIONS

PETRA-MRA, with better visualization of aneurysms and lower acoustic noise levels than TOF-MRA, showed a superior diagnostic performance for depicting saccular UIAs.